We study online convex optimization in the unbounded setting where neither
predictions nor gradient are constrained. The goal is to simultaneously adapt
to both the sequence of gradients and the comparator. We fi
文章探讨带有噪声梯度反馈的非平稳随机优化框架,在比较序列变化的动态策略中,研究在线学习算法的动态后悔,并引入了 Total Variation ball 等新颖变分约束来建模比较序列,并基于基于小波的非参数回归理论,设计出一个多项式时间算法,并证明了该算法达到了几乎最优的动态后悔,该策略适应未知的半径。